Exploring Visual and Motion Saliency for Automatic Video Object Extraction

Li, Wei-Te; Chang, Haw-Shiuan; Lien, Kuo-Chin; Chang, Hui-Tang; Wang, Y. F.

doi:10.1109/tip.2013.2253483

Cited by 164 publications

(23 citation statements)

References 35 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, given an arbitrary video sequence, the focal length of camera is often unknown. Inspired by salient object detection methods on static images [43], [44], [45], [46], salient motion detection methods [5], [47] have been applied on optical flow field for moving object segmentation, where pixels with high motion contrast are classified as foreground. Due to the lack of object information, it cannot handle moving background (e.g.…”

Section: Motion Segmentationmentioning

confidence: 99%

Unsupervised Online Video Object Segmentation With Motion Property Understanding

Zhuo

Cheng

Zhang

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Unsupervised video object segmentation aims to automatically segment moving objects over an unconstrained video without any user annotation. So far, only few unsupervised online methods have been reported in literature and their performance is still far from satisfactory, because the complementary information from future frames cannot be processed under online setting. To solve this challenging problem, in this paper, we propose a novel Unsupervised Online Video Object Segmentation (UOVOS) framework by construing the motion property to mean moving in concurrence with a generic object for segmented regions. By incorporating salient motion detection and object proposal, a pixel-wise fusion strategy is developed to effectively remove detection noise such as dynamic background and stationary objects. Furthermore, by leveraging the obtained segmentation from immediately preceding frames, a forward propagation algorithm is employed to deal with unreliable motion detection and object proposals. Experimental results on several benchmark datasets demonstrate the efficacy of the proposed method. Compared to the state-of-the-art unsupervised online segmentation algorithms, the proposed method achieves an absolute gain of 6.2%. Moreover, our method achieves better performance than the best unsupervised offline algorithm on the DAVIS-2016 benchmark dataset. Our code is available on the project website: https://github.com/visiontao/uovos.

show abstract

Section: Motion Segmentationmentioning

confidence: 99%

Unsupervised Online Video Object Segmentation With Motion Property Understanding

Zhuo

Cheng

Zhang

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Motion vector analysis has been used elsewhere for grouping moving pixels into objects based on spatio-temporal parameters [15] or vector magnitude and phase [16]. Probabilistic frameworks for aggregating vectors in a Markov random field [17] and tracking these over time [18] have been explored. Aggregations of mid-level primitives to form coherent salient objects under an energy maximization scheme was proposed in [19].…”

Section: Related Workmentioning

confidence: 99%

A particle filtering approach to salient video object localization

Gray

James

Collomosse

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

We describe a novel fully automatic algorithm for identifying salient objects in video based on their motion. Spatially coherent clusters of optical flow vectors are sampled to generate estimates of affine motion parameters local to super-pixels identified within each frame. These estimates, combined with spatial data, form coherent point distributions in a 5D solution space corresponding to objects or parts there-of. These distributions are temporally denoised using a particle filtering approach, and clustered to estimate the position and motion parameters of salient moving objects in the clip. We demonstrate localization of salient object/s in a variety of clips exhibiting moving and cluttered backgrounds.

show abstract

“…Human detection is to orient the pedestrian in video sequence or static image, it has become the hot research topic on computer vision, and also the difficulty due to the rigid and soft features of human and influenced by the posture, appearance, light, shade and other factors [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

A kind of Rapid Robust Human Detection Algorithm for the Interested Area

Rothenberg¹,

Shen²,

Yin³

et al. 2017

Proceedings of the 2017 7th International Conference on Applied Science, Engineering and Technology (ICASET 2017)

View full text Add to dashboard Cite

A kind of rapid two-level human detection algorithm based on the interested area was proposed in the paper, the coarse-level classifier was obtained via using the cascade training of multi-scale direction feature and Adaboost to extract the possibly human interested area, the decomposition and dimension reduction were realized via nonnegative matrix, and the précised classifier was obtained via the cascade training of dimension reduction feature and intersection kernel support vector machine to detect the human precisely. The experiment on INRIA public test set showed that the algorithm proposed in the paper improved the detection accuracy and greatly reduced the detection time when compared with the currently representative algorithm.

show abstract

Exploring Visual and Motion Saliency for Automatic Video Object Extraction

Cited by 164 publications

References 35 publications

Unsupervised Online Video Object Segmentation With Motion Property Understanding

Unsupervised Online Video Object Segmentation With Motion Property Understanding

A particle filtering approach to salient video object localization

A kind of Rapid Robust Human Detection Algorithm for the Interested Area

Contact Info

Product

Resources

About